mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
a6f67e1a65
* Add Math Evaluation with Judge Model Evaluator * Add Math Evaluation with Judge Model Evaluator * Add Math Evaluation with Judge Model Evaluator * Add Math Evaluation with Judge Model Evaluator * Fix Llama-3 meta template * Fix MATH with JudgeLM Evaluation * Fix MATH with JudgeLM Evaluation * Fix MATH with JudgeLM Evaluation * Fix MATH with JudgeLM Evaluation --------- Co-authored-by: liuhongwei <liuhongwei@pjlab.org.cn>
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
|
from opencompass.datasets import MATHDataset, MATHEvaluator, math_postprocess
|
|
|
|
QUERY_TEMPLATE = """
|
|
Solve the following math problem step by step. The last line of your response should be of the form ANSWER: $ANSWER (without quotes) where $ANSWER is the answer to the problem.
|
|
{problem}
|
|
Remember to put your answer on its own line after "ANSWER:", and you do not need to use a \\boxed command.
|
|
""".strip()
|
|
|
|
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
|
|
|
|
math_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
|
|
template=dict(round=[
|
|
dict(role="HUMAN", prompt=QUERY_TEMPLATE),
|
|
])),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer, max_out_len=1024))
|
|
|
|
math_eval_cfg = dict(
|
|
evaluator=dict(type=MATHEvaluator), pred_postprocessor=dict(type=math_postprocess))
|
|
|
|
math_datasets = [
|
|
dict(
|
|
type=MATHDataset,
|
|
abbr='math',
|
|
path='./data/math/math.json',
|
|
reader_cfg=math_reader_cfg,
|
|
infer_cfg=math_infer_cfg,
|
|
eval_cfg=math_eval_cfg)
|
|
] |